tfp.experimental.bijectors.forward_log_det_jacobian_ratio

Computes p.fldj(x, ndims) - q.fdlj(y, ndims), numerically stably.

tfp.experimental.bijectors.forward_log_det_jacobian_ratio(
    p, x, q, y, event_ndims, p_kwargs=None, q_kwargs=None
)

p_kwargs and q_kwargs are passed to the registered fldj_ratio_fn. The fallback implementation passes them to the forward_log_det_jacobian methods of p and q.

Args
p	A bijector instance.
x	A tensor from the preimage of p.forward.
q	A bijector instance of the same type as p, with matching shape.
y	A tensor from the preimage of q.forward.
event_ndims	The number of right-hand dimensions comprising the event shapes of x and y.
p_kwargs	Keyword args to pass to p.
q_kwargs	Keyword args to pass to q.

Returns
fldj_ratio	log ((abs o det o jac p)(x) / (abs o det o jac q)(y)), i.e. in TFP code, p.forward_log_det_jacobian(x, event_ndims) - q.forward_log_det_jacobian(y, event_ndims). In some cases this will be computed with better than naive numerical precision, e.g. by moving differences inside of a sum reduction.